The idea behind the necessity of switching from the widely used Global Positioning System (GPS) to NavIC (Navigation with Indian Constellation) is presented in this paper. The development of new navigation systems for Urban Air Mobility (UAM) applications is crucial for enabling reliable and efficient aerial transportation solutions. The AeroTrail project aims to build Unmanned Aerial Vehicles (UAVs) for tasks such as surveillance and communication relays in urban environments. This paper contributes to the AeroTrail project by investigating the feasibility and benefits of integrating NavIC for enhanced UAV navigation in urban environments. Furthermore, it focuses on the critical aspect of route planning by evaluating the effectiveness of various machine learning classification techniques to predict optimal and sustainable flight routes based on unique operational factors, particularly the correlation between flight characteristics and CO2 emissions. This research aims to identify the most suitable prediction models that can ultimately inform an automated route planning mechanism aligned with both efficiency and environmental considerations.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

ML-Driven Analysis of NavIC-Based Tracking for Route Optimization in Urban Air Mobility

  • Vishvesh Paresh Modcoicar,
  • Trupti Baraskar

摘要

The idea behind the necessity of switching from the widely used Global Positioning System (GPS) to NavIC (Navigation with Indian Constellation) is presented in this paper. The development of new navigation systems for Urban Air Mobility (UAM) applications is crucial for enabling reliable and efficient aerial transportation solutions. The AeroTrail project aims to build Unmanned Aerial Vehicles (UAVs) for tasks such as surveillance and communication relays in urban environments. This paper contributes to the AeroTrail project by investigating the feasibility and benefits of integrating NavIC for enhanced UAV navigation in urban environments. Furthermore, it focuses on the critical aspect of route planning by evaluating the effectiveness of various machine learning classification techniques to predict optimal and sustainable flight routes based on unique operational factors, particularly the correlation between flight characteristics and CO2 emissions. This research aims to identify the most suitable prediction models that can ultimately inform an automated route planning mechanism aligned with both efficiency and environmental considerations.